Triple
T25682623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Novena to Our Lady of Lourdes |
E643980
|
entity |
| Predicate | oftenPrayedBy |
P162109
|
FINISHED |
| Object | Catholic prayer groups |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Catholic prayer groups | Statement: [Novena to Our Lady of Lourdes, oftenPrayedBy, Catholic prayer groups]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenPrayedBy Context triple: [Novena to Our Lady of Lourdes, oftenPrayedBy, Catholic prayer groups]
-
A.
oftenPrayedBy
chosen
Indicates that the subject is frequently the one who prays to or for the object.
-
B.
praysIn
Indicates that an entity performs the act of praying within or at a particular place or setting.
-
C.
prayedDuring
Indicates that one entity performed prayer at some time within the duration of another specified event or time interval.
-
D.
associatedPrayer
Indicates a relationship where a specific prayer is linked or connected to another entity, such as an event, object, person, or religious context.
-
E.
praysFor
Indicates that one entity directs prayers or spiritual petitions on behalf of another entity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e77e8046888190b07ffa58c7e2c37a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f627aedf548190bc9f53c8a2d67b50 |
completed | May 2, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69f623a4e1048190bbb8dd1253fdcee9 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 21, 2026, 8:03 p.m.